Collaborative filtering plays an important role in predicting consumer preferences in the electronic market. Most of the users purchased the products in the electronic market with the help of the Internet of Things (IoT) and Social Networks. Predicting consumer preference with the consumer’s history is a vital challenge in the recommendation systems. The researchers propose varieties of collaborative filtering techniques, but the accuracy of the results is poor. The main aim of this paper is to propose a deep learning with collaborative filtering technique for the recommendation system to Predicting User preferences from the IoT devices and Social Networks that are beneficial for users based on their preferences in electronic markets. In this paper similarity, neighborhood-based collaborative filtering model (SN-CFM) is introduced. The introduced model recommends the products by predicting consumer preferences based on the similarity of the consumers and neighborhood products. In addition, the introduced deep learning concept gets the information from the previous analysis before making rating to the items. The introduced SN-CFM model compared with other existing recommendation approaches. The results prove that the efficiency of the introduced model.

中文翻译：

---

使用基于深度学习的协作过滤技术，基于物联网和社交网络预测电子市场中的消费者偏好

协作过滤在预测电子市场中的消费者偏好方面起着重要作用。大多数用户借助物联网（IoT）和社交网络在电子市场购买了产品。用消费者的历史预测消费者的喜好是推荐系统中的重要挑战。研究人员提出了多种协作过滤技术，但结果的准确性很差。本文的主要目的是为推荐系统提出深度学习和协作过滤技术，以从物联网设备和社交网络预测用户的偏好，这些偏好基于用户在电子市场中的偏好而受益。在本文相似度中，介绍了基于邻域的协同过滤模型（SN-CFM）。引入的模型通过基于消费者和附近产品的相似性来预测消费者的偏好来推荐产品。此外，引入的深度学习概念会在对项目进行评分之前从先前的分析中获取信息。与其他现有推荐方法相比，引入的SN-CFM模型。结果证明了该模型的有效性。